Learning More for Free - A Multi Task Learning Approach for Improved Pathology Classification in Capsule Endoscopy
This work addresses data scarcity in medical imaging for improved computer-aided diagnosis in capsule endoscopy, though it is incremental in applying existing multi-task learning techniques to a specific domain.
The paper tackles the problem of limited data for multi-pathology classification in wireless capsule endoscopy by combining self-supervision with full supervision in a multi-task learning approach, achieving a 7.5% improvement in classification accuracy compared to baseline methods.
The progress in Computer Aided Diagnosis (CADx) of Wireless Capsule Endoscopy (WCE) is thwarted by the lack of data. The inadequacy in richly representative healthy and abnormal conditions results in isolated analyses of pathologies, that can not handle realistic multi-pathology scenarios. In this work, we explore how to learn more for free, from limited data through solving a WCE multicentric, multi-pathology classification problem. Learning more implies to learning more than full supervision would allow with the same data. This is done by combining self supervision with full supervision, under multi task learning. Additionally, we draw inspiration from the Human Visual System (HVS) in designing self supervision tasks and investigate if seemingly ineffectual signals within the data itself can be exploited to gain performance, if so, which signals would be better than others. Further, we present our analysis of the high level features as a stepping stone towards more robust multi-pathology CADx in WCE.